Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2) (remove)
Year of publication
- 2020 (2) (remove)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- artificial intelligence (1)
- biomarker variability (1)
- creatine kinase (1)
- endurance (1)
- exercise intensity (1)
- internal load (1)
- monitoring (1)
- point of care testing (1)
- precision training (1)
- prediction (1)
Institute
- Institut für Sportwissenschaft (2) (remove)
The aim of this study was to investigate inter-day and -week as well as intra- and inter-individual variation of selected biomarkers in high-performance youth soccer players to assist practitioners interpreting player’s internal load to counteract underperformance and unwanted health risks. Eleven male youth soccer players were tested multiple times during two 3-week periods at midpoint (3-wkmid) and at the end (3-wkend) of the first half of a German under-19 1. Bundesliga season. The levels of creatine kinase (CK), urea, and C-reactive protein (CRP) were measured during 3-wkmid and 3-wkend each Monday, Wednesday, and Friday. In 3-wkmid the CK median was 14% higher (241 vs. 212 U/L) compared to 3-wkend (P = 0.26, ES = 0.16). Overall, the medians of CK, urea (P = 0.59, ES = 0.08), and CRP (P = 0.56, ES = 0.10) during 3-wkmid did not differ to the values of 3-wkend. Daily coefficient of variations (CVs) ranged from 22 to 71% (CK), 17 to 37% (urea), and 9 to 164% (CRP). Individual medians ranged from 101 to 350 U/L (CK), 23 to 50 mg/dL (urea), and 0.6 to 1.1 mg/L (CRP). High intra-individual variability was demonstrated by large intra-individual CVs (medians: CK 50%, urea 18%, and CRP 45%). Our data show (i) large inter-day and inter-week variability of all biomarkers, depending on the external load and (ii) considerable inter- and intra-individual parameter variations. Creatine kinase concentrations could sensitively reflect soccer-specific loads during the season.
The rating of perceived exertion (RPE) is a subjective load marker and may assist in individualizing training prescription, particularly by adjusting running intensity. Unfortunately, RPE has shortcomings (e.g., underreporting) and cannot be monitored continuously and automatically throughout a training sessions. In this pilot study, we aimed to predict two classes of RPE (≤15 “Somewhat hard to hard” on Borg’s 6–20 scale vs. RPE >15 in runners by analyzing data recorded by a commercially-available smartwatch with machine learning algorithms. Twelve trained and untrained runners performed long-continuous runs at a constant self-selected pace to volitional exhaustion. Untrained runners reported their RPE each kilometer, whereas trained runners reported every five kilometers. The kinetics of heart rate, step cadence, and running velocity were recorded continuously ( 1 Hz ) with a commercially-available smartwatch (Polar V800). We trained different machine learning algorithms to estimate the two classes of RPE based on the time series sensor data derived from the smartwatch. Predictions were analyzed in different settings: accuracy overall and per runner type; i.e., accuracy for trained and untrained runners independently. We achieved top accuracies of 84.8 % for the whole dataset, 81.8 % for the trained runners, and 86.1 % for the untrained runners. We predict two classes of RPE with high accuracy using machine learning and smartwatch data. This approach might aid in individualizing training prescriptions.